检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Su, Yifei An, Dong Chen, Kehan Yu, Weichen Ning, Baiyang Ling, Yonggen Huang, Yan Wang, Liang School of Artificial Intelligence University of Chinese Academy of Sciences China MAIS Institute of Automation of Chinese Academy of Sciences China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Electrical and Computer Engineering Department Carnegie Mellon University United States Robotics X Tencent Shenzhen China

ISBN: (纸本)157735897X

Aerial Vision-Dialog Navigation (AVDN) is a new task that requires drones to navigate to a target location based on human-robot dialog history. This paper focuses on the critical fine-grained cross-modal alignment problem in AVDN, requiring the drone to align language entities with visual landmarks in top-down views. To achieve this, we first construct a Fine-Grained AVDN (FG-AVDN) dataset via a semi-automatic annotation pipeline, providing diverse multimodal annotations at the entity-landmark level. Based on this, a novel Fine-grained Entity-Landmark Alignment (FELA) method is proposed to learn the cross-modal alignment explicitly. Concretely, FELA first boosts the drone’s visual understanding with a precise semantic grid representation, which captures the environmental semantics and spatial structure simultaneously. Subsequently, to learn the entity-landmark alignment, we devise cross-modal auxiliary tasks from three perspectives, including grounding, captioning, and contrastive learning. Extensive experiments demonstrate that our explicit entity-landmark alignment learning is beneficial for AVDN. As a result, FELA achieves leading performance with 3.2% SR and 4.9% GP improvements over prior arts. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

ORCHNet: A Robust Global Feature Aggregation approach for 3D LiDAR-based Place recognition in Orchards

arXiv

引用

arXiv 2023年

作者： Barros, T. Garrote, L. Conde, P. Coombes, M.J. Liu, C. Premebida, C. Nunes, U.J. The University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Portugal The Dept. of Aeronautical and Automotive Engineering LUCAS Lab. Loughborough University United Kingdom

Robust and reliable place recognition and loop closure detection in agricultural environments is still an open problem. In particular, orchards are a difficult case study due to structural similarity across the entire field. In this work, we address the place recognition problem in orchards resorting to 3D LiDAR data, which is considered a key modality for robustness. Hence, we propose ORCHNet, a deep-learning-based approach that maps 3D-LiDAR scans to global descriptors. Specifically, this work proposes a new global feature aggregation approach, which fuses multiple aggregation methods into a robust global descriptor. ORCHNet is evaluated on real-world data collected in orchards, comprising data from the summer and autumn seasons. To assess the robustness, We compare ORCHNet with state-of-the-art aggregation approaches on data from the same season and across seasons. Moreover, we additionally evaluate the proposed approach as part of a localization framework, where ORCHNet is used as a loop closure detector. The empirical results indicate that, on the place recognition task, ORCHNet outperforms the remaining approaches, and is also more robust across seasons. As for the localization, the edge cases where the path goes through the trees are solved when integrating ORCHNet as a loop detector, showing the potential applicability of the proposed approach in this task. The code will be publicly available at:https://***/Cybonic/***. © 2023, CC BY.

关键词： Orchards

来源：评论

学校读者我要写书评

暂无评论

Direct Search Algorithm for Load Frequency Control of a Time-Delayed Electric Vehicle Aggregator

引用

IEEE Transactions on Industry Applications 2022年第2期59卷 1-11页

作者： Abolpour R. Torabi K. Dehghani M. Vafamand N. Javadi M.S. Wang F. Catalao J.P.S. School of Electrical and Computer Engineering Shiraz University Shiraz Iran Institute for Systems and Computer Engineering Technology and Science (INESC TEC) Porto Portugal Department of Electrical Engineering North China Electric Power University (NCEPU) Baoding China Faculty of Engineering University of Porto (FEUP) and INESC TEC Porto Portugal

This paper addresses the topic of frequency regulation of a single-area power system connected to an electric vehicle (EV) aggregator over a non-ideal communication network. It is considered that the command control action is received by the EV aggregator with constant delay and the power system includes uncertain parameters. Due to the presence of uncertainties and the delay term, the frequency regulation problem is non-convex and hard to solve. The present approaches in the literature convert the non-convex control design problem into a convex problem with a set of Linear Matrix Inequalities (LMIs), which is conservative and in many cases results infeasibility. In this paper, an innovative iterative algorithm, called direct search, is employed for the time-delayed system to design the unknown parameters of a pre-assumed controller. The controller choice is not limited and various controllers' structures can be assumed. Without loss of generality, a proportional-integral (PI) controller is designed. The novel direct search algorithm can determine a feasible solution whenever at least one solution lays in the design space. Hence, by selecting a wide design space, we can anticipate that the PI controller guarantees closed-loop stability. Numerical simulations are carried out to demonstrate the performance of the developed controller compared to the state-of-the-art approach. IEEE

关键词： Asymptotic stability Delay effects Delays direct search algorithm electric vehicle aggregator Frequency control Load frequency control Lyapunov Krasovskii Functional (LKF) Power system stability Renewable energy sources robust control Stability criteria time delay

来源：评论

学校读者我要写书评

暂无评论

Allocation of Control Authority Between Dynamic Inversion and Reinforcement Learning for Autonomous Helicopter Aerial Refueling

Allocation of Control Authority Between Dynamic Inversion an...

引用

American Control Conference (ACC)

作者： Damsara Jayarathne Santiago Paternain Sandipan Mishra department of Mechanical Aerospace and Nuclear Engineering Rensselaer Polytechnic Institute Troy NY Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

The typical control architecture for autonomous helicopter operations consists of an inner loop for attitude stabilization and an outer loop control for lateral/longitudinal dynamics. In this paper, we focus on the design of the outer loop controller for helicopter aerial refueling. In order to alleviate the drawbacks of solely model-based or pure data-driven controllers, a residual reinforcement learning framework is presented where a model-based controller is combined with a reinforcement learning (RL) controller. These two controllers work in tandem to leverage the advantages of both the model-based and data-driven components. However, this requires appropriately allocating control authority to each controller (the maximum/minimum control authority and/or controller parameters), which are typically determined through time-consuming heuristic methods. Recognizing the need for a systematic approach to achieve reasonable harmony between the two control strategies, here we present an analytical (model-based) approach that facilitates the selection of the outer loop control gains for the model-based (dynamic inversion) controller along with appropriate bounds for the (data-driven) RL control input. We explicitly incorporate uncertainty bounds on the drogue motion and the maximum allowable acceleration of the aircraft into the control design. Finally, we showcase the applicability of the methodology through a simulation study.

关键词： Analytical models Uncertainty Systematics Control design Atmospheric modeling Helicopters Dynamics

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for a Class of Cascade Dynamical systems

arXiv

引用

arXiv 2024年

作者： Rabiei, Shima Mishra, Sandipan Paternain, Santiago Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States Department of Mechanical Aerospace and Nuclear Engineering Rensselaer Polytechnic Institute United States

This work considers the problem of transfer learning in the context of reinforcement learning. Specifically, we consider training a policy in a reduced order system and deploying it in the full state system. The motivation for this training strategy is that running simulations in the full-state system may take excessive time if the dynamics are complex. While transfer learning alleviates the computational issue, the transfer guarantees depend on the discrepancy between the two systems. In this work, we consider a class of cascade dynamical systems, where the dynamics of a subset of the state-space influence the rest of the states but not vice-versa. The reinforcement learning policy learns in a model that ignores the dynamics of these states and treats them as commanded inputs. In the full-state system, these dynamics are handled using a classic controller (e.g., a PID). These systems have vast applications in the control literature and their structure allows us to provide transfer guarantees that depend on the stability of the inner loop controller. Numerical experiments on a quadrotor support the theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep nonparametric estimation of operators between infinite dimensional spaces

引用

The Journal of Machine Learning Research 2024年第1期25卷 1239-1305页

作者： Hao Liu Haizhao Yang Minshuo Chen Tuo Zhao Wenjing Liao Department of Mathematics Hong Kong Baptist University Hong Kong Department of Mathematics and Department of Computer Science University of Maryland College Park Department of Electrical and Computer Engineering Princeton University School of Industrial and Systems Engineering Georgia Institute of Technology School of Mathematics Georgia Institute of Technology

Learning operators between infinitely dimensional spaces is an important learning task arising in machine learning, imaging science, mathematical modeling and simulations, etc. This paper studies the nonparametric estimation of Lipschitz operators using deep neural networks. Non-asymptotic upper bounds are derived for the generalization error of the empirical risk minimizer over a properly chosen network class. Under the assumption that the target operator exhibits a low dimensional structure, our error bounds decay as the training sample size increases, with an attractive fast rate depending on the intrinsic dimension in our estimation. Our assumptions cover most scenarios in real applications and our results give rise to fast rates by exploiting low dimensional structures of data in operator estimation. We also investigate the influence of network structures (e.g., network width, depth, and sparsity) on the generalization error of the neural network estimator and propose a general suggestion on the choice of network structures to maximize the learning efficiency quantitatively.

关键词： deep neural networks nonparametric estimation operator learning generalization error analysis

来源：评论

学校读者我要写书评

暂无评论

Study of monolithically integrated 940 nm AlGaAs distributed Bragg reflectors on graded GaAsP/bulk Si substrates

引用

Optical Materials Express 2023年第4期13卷 1077-1091页

作者： Guo, Jia Zhao, Yunlong Feifel, Markus Cheng, Hao-Tien Yang, Yun-Cheng Chrostowski, Lukas Lackner, David Wu, Chao-Hsin Xia, Guangrui Department of Materials Engineering The University of British Columbia VancouverBCV6 T 1Z4 Canada Fraunhofer Institute for Solar Energy Systems ISE Heidenhofstraße 2 Freiburg79110 Germany Graduate Institute of Electronics Engineering National Taiwan University Taiwan Graduate Institute of Photonics and Optoelectronics National Taiwan University Taiwan Department of Electrical and Computer Engineering University of British Columbia VancouverBCV6 T 1Z4 Canada

We report the fabrication of monolithically integrated 940 nm AlGaAs distributed Bragg reflectors (DBRs) on graded GaAsP/Si substrates. Low-density surface bumps and cross-hatch patterns were observed on the DBR surfaces. Cross-sectional DBR layers are smooth and flat. The reflectance spectra of the GaAsP/Si DBRs have lower intensities than those of the GaAs DBRs and have double peaks. Transfer matrix method calculations, surface scratch and polishing tests were conducted, which suggest that the surface cross-hatch was the cause of the inferior DBR reflectance spectra. © 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning Based Classification of Engagement for Child-Robot Interaction

Deep-Learning Based Classification of Engagement for Child-R...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Gabriela Simões Ana Lopes Carlos Carona Ricardo Pereira Urbano J. Nunes Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal Polytechnic Institute of Tomar Portugal Center for Research in Neuropsychology and Cognitive and Behavioral Intervention University of Coimbra

This work aims to describe the research and development of an engagement classification system based on emotion recognition through the use of facial expressions, to be used in robotic applications for children interacting with a NAO humanoid robot during therapy sessions. An emotion classification model based on different Convolution Neural Networks (CNN) architectures was first fed by faces provided from different public datasets to train and validate the emotion classification models. Two engagement classification methodologies are proposed: Method-1 first classifies 7-classes of emotions, using the ConvNeXt network, and then infers the levels of engagement based on the affective model developed by [1]; Method-2 employs the same classification network to directly classify the four levels of engagement. The results obtained for both engagement classification methodologies using the CAFE dataset proved their effectiveness, however Method-1 performs slightly better in terms of engagement classification accuracy. A novel child-robot activity with a NAO humanoid robot, that consists in a breathing-based relaxation exercise, is also proposed and the results of offline classification system showed to be promising, and with potential to be applied in psychology therapies in the future.

关键词： Emotion recognition Convolution Neural networks Medical treatment Humanoid robots Psychology Human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

Self-Organized Sensor Eggs for Decentralized Localization and Sensing on Vulcano Island – A Glimpse into Future Space Exploration with Swarms

Self-Organized Sensor Eggs for Decentralized Localization an...

引用

International Conference on Information Fusion

作者： Fabio Broghammer Thomas Wiedemann Siwei Zhang Armin Dammann Christian Gentner Petar Djuric Institute of Communications and Navigation German Aerospace Center (DLR) Germany Perception for Intelligent Systems Munich Institute of Robotics and Machine Intelligence TU Munich Germany Department of Electrical and Computer Engineering Stony Brook University USA

ISBN: (数字)9781737749769

ISBN: (纸本)9798350371420

Robotic swarms or portable sensor networks are emerging technologies for sensing physical processes that are spatially distributed- and temporally dynamic, both on Earth and in future Moon/Mars exploration missions. We develop a portable network composed of a multitude of self-organized “sensor eggs”. These eggs are equipped with ultra-wideband (UWB) transceivers, providing precise time and position information without additional infrastructures like Global Navigation Satellite systems (GNSSs). Each egg is additionally equipped with environmental sensors, for example, a Sulfur dioxide gas sensor to explore volcanic activity. We use a real time decentralized particle filter (DPF) to estimate the a-posteriori probability density functions (PDFs) of the egg positions. These PDFs are then used in a static state binary Bayes filter for estimating the gas sources with potentially complex structures such as cracks on the volcano surface. The proposed sensor network is verified with an in-field experiment at La Fossa volcano on the island of Vulcano, Italy, in 2023.

关键词： Location awareness Volcanic activity Probability density function Robot sensing systems Particle filters Transceivers Sensors Timing Surface cracks Ultra wideband technology

来源：评论

学校读者我要写书评

暂无评论

Programmable Switching of Fluids via Pre-Twisting

Programmable Switching of Fluids via Pre-Twisting

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Yijia Wu Markus P. Nemitz Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA Department of Mechanical and Materials Engineering Worcester Polytechnic Institute Worcester MA USA Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

Manipulating airflow is important for controlling pneumatically actuated soft robots, however, current switching techniques suffer from leakage under high pressure ( $> 200$ kPa) or require a complex fabrication process. We propose a new method for reliably and repeatably cutting off airflow by harnessing pre-loaded torsional forces applied to our tubing. The switching distance and hysteresis of our pre-twisted tubing are programmable by varying the tube length and the twisting angle. Our experiments demonstrate the use of pre-twisted tubing to implement CMOS equivalent fluidic switches configured as NOT-, AND-, and OR-gates, and a distance sensor for feedback control for the oscillation of a PneuNet. Our approach of pre-loading tubes with a torsional force allows for simplicity, integrated functionality, and the capability of manipulating high-pressure, fluidic signals mainly at the cost of tubing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：